Empathic Chatbot Response for Medical Assistance

Abstract

Is it helpful for a medical physical health chatbot to show empathy? How can a chatbot show empathy only based on short-term text conversations? We have investigated these questions by building two different medical assistant chatbots with the goal of providing a diagnosis for physical health problem to the user based on a short conversation. One chatbot was advice-only and asked only the necessary questions for the diagnosis without responding to the user's emotions. Another chatbot, capable of showing empathy, responded in a more supportive manner by analyzing the user's emotions and generating appropriate responses with a high empathic accuracy. Using the RoPE scale questionnaire for empathy perception in a human-robot interaction, our empathic chatbot was rated significantly better in showing empathy and was preferred by a majority of the preliminary study participants (N=12).

Artificial intelligence technologies and compassion in healthcare: A systematic scoping review

“…Nonetheless, empathy display and relational behavior are significant research themes in dialog systems development and robotics ( Kennedy et al, 2012 ; Liu and Sundar, 2018 ; Pepito et al, 2020 ; Kerruish, 2021 ). Studies with patients have shown that most people prefer medical assistant chatbots that mimic empathy ( Amini et al, 2013 ; Liu and Sundar, 2018 ; Daher et al, 2020 ), this is particularly true for users who are initially skeptical about machines possessing social cognitive capabilities. However, research in Korea ( Yun et al, 2021 ) shows there is a discrepancy between expressed behavioral intentions toward medical AI and implicit attitudes (detected in brain scans) which shows people respond differently to the same conversation if it is delivered by a human doctor or medical AI.…”

“…← Robot/artificial emotional response behaviours (artificial empathy) (Kennedy et al, 2012;Pepito et al, 2020;Kerruish, 2021;Montemayor et al, 2021) ← Empathetic chatbots (Amini et al, 2013;Liu and Sundar, 2018;Daher et al, 2020) ← Empathetic medical conversations (Yun et al, 2021) ← Web app that provides cancer disease related information to patients (Papadakos et al, 2017) ← AI-generated diagnosis information for radiology patients (Zhang et al, 2021) Health coaching (11 articles) ← Virtual health coaches (Kennedy et al, 2012;Bevilacqua et al, 2020), smoking cessation (He et al, 2022), weight-loss (Stein and Brooks, 2017), self-management of depression (Inkster et al, 2018), and chronic disease self-management (Hernandez, 2019) ← Therapeutic chatbots for mental health (Lee et al, 2019;Valtolina and Hu, 2021) ← Automated healthcare quality assessment e.g., sentiment analysis of patient feedback from diverse groups of service users (Doing- Harris et al, 2017;Rahim et al, 2021) ← Automated analysis of patient and family feedback captured by interactive patient care technology in hospitals (Clavelle et al, 2019) ← Automated analysis of online health communities to inform policy for patient self-care (Panzarasa et al, 2020) ← Automated evaluation of psychotherapy services linked to training, supervision, and quality assurance (Flemotomos et al, 2022;Xiao et al, 2015).…”

Evaluation of the Current State of Chatbots for Digital Health: Scoping Review

“…Perceptions of chatbots as less serious compared with real health care professionals might result in skepticism and reduced reliance on chatbot-driven information. A previous study discerned a preference for advice-only chatbots over empathic ones for self-diagnosis [ 36 ]. The potential lack of empathy perceived by chatbots could contribute to a diminished level of trust, highlighting the ongoing debate regarding the effectiveness of chatbots in web-based diagnosis and interventions.…”